© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114804
    Prev
    Next
    INDEX
    Explanations

    Juice Operations

    np_acts-logits-general · gemini-2.5-flash-lite

    converting FAQs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anded
    0.45
    on
    0.43
    т
    0.43
     props
    0.42
     consultative
    0.41
    icious
    0.41
    遮
    0.40
    兜
    0.39
     opts
    0.38
    MIDI
    0.38
    POSITIVE LOGITS
     которое
    0.52
     Elektrokhimiya
    0.51
     propiedad
    0.50
     Russel
    0.49
     darum
    0.49
     aprovech
    0.48
    প্রতিষ্ঠ
    0.48
     多く
    0.48
     Profesor
    0.47
     inaccessible
    0.46
    Activations Density 0.002%

    No Known Activations